Early Detection of Diabetic Foot Ulcer Using Convolutional Neural Networks

Abdelrahman Shata; Nidhal Abdulaziz

doi:10.1109/TENSYMP52854.2021.9550812

Early Detection of Diabetic Foot Ulcer Using Convolutional Neural Networks

Abdelrahman Shata
, Nidhal Abdulaziz

School of Engineering & Physical Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

4 Citations (Scopus)

Abstract

Diabetic Foot Ulcer is a very common problem that faces diabetic patients with almost 15 percent of these patients developing a foot ulcer at least once in their life. Diabetic patients tend to suffer from numbness and loss of sensation in their feet making it hard for them to self-detect the ulcer therefore an early detection method is needed. The approach conducted in this paper uses a 2-dimentional image as an input and using convolutional neural networks to analyze the images. The system will classify the input images into two states, no ulcer or the ulcer is present and in this case the location of the ulcer will be marked on the image. The system achieved an F1- score of 81.3% with an improvement of more than 7% from the F1-score achieved in the Diabetic Foot Ulcer Challenge 2020.

Original language	English
Title of host publication	2021 IEEE Region 10 Symposium
Publisher	IEEE
ISBN (Electronic)	9781665400268
DOIs	https://doi.org/10.1109/TENSYMP52854.2021.9550812
Publication status	Published - 4 Oct 2021
Event	2021 IEEE Region 10 Symposium - Jeju, Korea, Republic of Duration: 23 Aug 2021 → 25 Aug 2021

Conference

Conference	2021 IEEE Region 10 Symposium
Abbreviated title	TENSYMP 2021
Country/Territory	Korea, Republic of
City	Jeju
Period	23/08/21 → 25/08/21

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

SDG 3 Good Health and Well-being

Keywords

Artificial Intelligence
Convolutional Neural Networks
Diabetic Foot Ulcer
Image Processing

ASJC Scopus subject areas

Computer Science Applications
Computer Vision and Pattern Recognition
Information Systems and Management
Computer Networks and Communications
Energy Engineering and Power Technology
Electrical and Electronic Engineering
Instrumentation

Access to Document

10.1109/TENSYMP52854.2021.9550812

Cite this

@inproceedings{9bc59a5ccdb249bfb5e1e6860cd79fe4,

title = "Early Detection of Diabetic Foot Ulcer Using Convolutional Neural Networks",

abstract = "Diabetic Foot Ulcer is a very common problem that faces diabetic patients with almost 15 percent of these patients developing a foot ulcer at least once in their life. Diabetic patients tend to suffer from numbness and loss of sensation in their feet making it hard for them to self-detect the ulcer therefore an early detection method is needed. The approach conducted in this paper uses a 2-dimentional image as an input and using convolutional neural networks to analyze the images. The system will classify the input images into two states, no ulcer or the ulcer is present and in this case the location of the ulcer will be marked on the image. The system achieved an F1- score of 81.3\% with an improvement of more than 7\% from the F1-score achieved in the Diabetic Foot Ulcer Challenge 2020.",

keywords = "Artificial Intelligence, Convolutional Neural Networks, Diabetic Foot Ulcer, Image Processing",

author = "Abdelrahman Shata and Nidhal Abdulaziz",

note = "Publisher Copyright: {\textcopyright} 2021 IEEE.; 2021 IEEE Region 10 Symposium, TENSYMP 2021 ; Conference date: 23-08-2021 Through 25-08-2021",

year = "2021",

month = oct,

day = "4",

doi = "10.1109/TENSYMP52854.2021.9550812",

language = "English",

booktitle = "2021 IEEE Region 10 Symposium",

publisher = "IEEE",

address = "United States",

}

TY - GEN

T1 - Early Detection of Diabetic Foot Ulcer Using Convolutional Neural Networks

AU - Shata, Abdelrahman

AU - Abdulaziz, Nidhal

PY - 2021/10/4

Y1 - 2021/10/4

N2 - Diabetic Foot Ulcer is a very common problem that faces diabetic patients with almost 15 percent of these patients developing a foot ulcer at least once in their life. Diabetic patients tend to suffer from numbness and loss of sensation in their feet making it hard for them to self-detect the ulcer therefore an early detection method is needed. The approach conducted in this paper uses a 2-dimentional image as an input and using convolutional neural networks to analyze the images. The system will classify the input images into two states, no ulcer or the ulcer is present and in this case the location of the ulcer will be marked on the image. The system achieved an F1- score of 81.3% with an improvement of more than 7% from the F1-score achieved in the Diabetic Foot Ulcer Challenge 2020.

AB - Diabetic Foot Ulcer is a very common problem that faces diabetic patients with almost 15 percent of these patients developing a foot ulcer at least once in their life. Diabetic patients tend to suffer from numbness and loss of sensation in their feet making it hard for them to self-detect the ulcer therefore an early detection method is needed. The approach conducted in this paper uses a 2-dimentional image as an input and using convolutional neural networks to analyze the images. The system will classify the input images into two states, no ulcer or the ulcer is present and in this case the location of the ulcer will be marked on the image. The system achieved an F1- score of 81.3% with an improvement of more than 7% from the F1-score achieved in the Diabetic Foot Ulcer Challenge 2020.

KW - Artificial Intelligence

KW - Convolutional Neural Networks

KW - Diabetic Foot Ulcer

KW - Image Processing

UR - https://www.scopus.com/pages/publications/85117439337

U2 - 10.1109/TENSYMP52854.2021.9550812

DO - 10.1109/TENSYMP52854.2021.9550812

M3 - Conference contribution

AN - SCOPUS:85117439337

BT - 2021 IEEE Region 10 Symposium

PB - IEEE

T2 - 2021 IEEE Region 10 Symposium

Y2 - 23 August 2021 through 25 August 2021

ER -

Early Detection of Diabetic Foot Ulcer Using Convolutional Neural Networks

Abstract

Conference

UN SDGs

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this